01
It starts by itself
weekly source briefing. Runs in Claude Code routine or cron.
- ↻ weekly source briefing
0 8 * * 1
teng-lin · 10K installsNotebookLM skill
Runs by itself, once a week.
A fresh briefing from your new sources every week.
Install the NotebookLM skill and make it a habit: follow https://gethabit.dev/skills/teng-lin/notebooklm.md
- 1Copy
- 2Paste into Claude Code, Codex or Cursor
- 3It runs by itself
10K installs20K starsMIT licenceSource on GitHub ↗
NotebookLM
by teng-lin · 10K installs
The skill
Adds sources to Gemini Notebook and gets answers or audio from them.
Only when you ask.
Time saved
A fresh briefing from your new sources every week. Time saved on reading.
↻ Runs by itselfonce a week
How the habit works.
You don't have to.
When does it start? How does it check its work? What does it remember?
One run, step by step.
Then it stops.
Stops after one notebook and one generated artifact per run; failed generation is not retried without your OK.
- 01
Check auth
The agent runs the auth check with --test and --json and stops unless it reports ok.
- 02
Add new sources
Each new input goes in with source add, pinned to the notebook ID, and its source ID is kept.
- 03
Wait for ready
It runs source wait for every new source and goes on only when all are ready.
- 04
Ask for approval
Before generation, long waits or downloads that were not already authorized, it asks you to confirm.
- 05
Ask or generate
It runs an ID-pinned ask for analysis, or generate with the chosen type, such as audio or report.
- 06
Wait and download
It runs artifact wait on the exact artifact ID, then downloads only that artifact.
- 07
Log the IDs
Notebook, source and artifact IDs and their status go onto the board.
What it may do.
Nothing more.
It writes only in its own folder and asks you before anything goes out.
- Writes only inloops/notebooklm-briefing-loop/**, the downloaded artifact file
- Talks tono outside service
- Sendsnothing
- Your OKIt asks you before anything goes out.
Is it for you?
Use it when it fits.
Read both lists. If the left one sounds like you, the NotebookLM skill helps.
Use it when
- ✓ You manage Gemini Notebook sources
- ✓ You want audio or report artifacts
- ✓ You automate grounded research
Skip it when
- – You need the generic Gemini API
- – You need unrelated content creation
NotebookLM skill, answered.
Why does it ask before generating?
The skill treats generation, long waits and downloads as actions that need clear consent.
Does it delete old notebooks?
No. Deletion is a destructive action and is left out of this loop.
What happens on a rate limit?
The task ID is kept, the status is inspected and you get a note; there is no automatic retry.
Are credentials safe?
The skill says to never print, log or commit the auth files, and the loop follows that.
How do I install the NotebookLM skill?
Copy the prompt at the top into your agent. It installs the skill from teng-lin/notebooklm-py and sets up the habit. Or run npx skills add teng-lin/notebooklm-py --skill notebooklm.
Is the NotebookLM skill free?
Yes. It is published under MIT. Habit is free too.
NotebookLM. Now as a habit.
Install the NotebookLM skill and make it a habit: follow https://gethabit.dev/skills/teng-lin/notebooklm.md
All teng-lin skills →More notes skills →
Works in
- Claude Code
- Codex
- Cursor
- ChatGPT
- Claude app
Made by teng-lin, published under MIT. Habit links to the original and never changes it. Is this your skill?